agentleFS
Lixiuxiu559Lixiuxiu559/AgentForge/skills/architecture-design/SKILL.md

architecture-design

Skill4 starsChanged 45 days agoMITView on GitHub

将需求、原型或明确技术问题转为完整的系统设计,默认交付含可见图示的 HTML。比较可行方案并由用户决定关键取舍,再完成整体与必要专项设计、风险验证和一致性复核;复杂专项可委派子 agent。适用于系统设计、技术方案、接口或数据模型设计及方案评审;不实施生产代码或部署,不做全仓架构机会扫描。

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use results-report, daily-coding and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Galaxy-DawnSkill

    results-report

    This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.

    Also in 3 projects that use this

  • Clay-HHKSkill

    daily-coding

    Daily coding assistant that auto-triggers when writing/modifying code, providing a core checklist.

    Also in 3 projects that use this

  • Clay-HHKSkill

    kaggle-learner

    This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.

    Also in 3 projects that use this

  • kharlamenkodevSkill

    bug-detective

    Also in 4 projects that use this

  • gclmSkill

    observability-design

    Design logs, metrics, traces, alerts, and debugging signals so systems can be operated and diagnosed before incidents expose blind spots.

    Also in 3 projects that use this

  • Google CloudSkill

    citation-verification

    Verify that citations in a document resolve to real records and that claimed titles match. Use before trusting a document's reference list.

    Also in 4 projects that use this

  • +2 more from Clay-HHK

The file

Files
SKILL.md

统一架构设计

职责与输入

承担本次范围内系统设计的完整性责任,确定跨模块规则、关键技术路线及可行性,使使用者不必重新补定共享契约和数据语义;普通函数组织等局部实现不预先限定。

独立使用需求、PRD、原型、已有方案或工程事实,不要求固定前置文档/技能,也不指定或调用下一技能。单端任务不凭空增加另一端;评审已有方案时聚焦相关问题,不重做无关设计。

只交付设计,可给契约、Schema、迁移草案和关键伪代码;不写生产实现、执行数据库变更、调整版本或发布。单纯解释概念、绘制已有架构或按已定方案编码不启动完整流程。

1. 建立依据与约束

按需读取项目指令、相关需求、原型、契约、ADR、规范和受影响实现/测试。关键字段、兼容性与约束核对真实来源,不把文档或代码现状自动当成正确需求。

区分事实、设计建议和假设;数据库设计比较可取得的迁移与实际 Schema,没有连接则标明环境未核实。按 质量目标与风险验证 识别决定架构的关键场景,不编造性能、容量或部署事实。

只追问会影响业务规则、边界、兼容性或关键取舍的缺口,可继续独立部分;材料充分不等于用户已经选择技术路线。

2. 比较方案,与用户确定方向

按 方案比较与决策 展示真实可行方案的优缺点、成本、风险与推荐依据,由用户决定重大取舍。用户选择前只推进独立取证或候选探索,不沿推荐项定稿或深化依赖部分;已有明确选择/限定授权直接沿用,不重复确认。

3. 形成整体方案并验证风险

在已确认或授权的方向内,按 整体方案要点 建立统一基线,说明目标范围、模块边界、关键流程、数据归属、共享契约、主要取舍与依赖。整体初稿不代表设计完成。

有原型时建立“页面/操作/状态 → 技术支撑”对应,区分服务端数据、输入、派生值和纯展示状态,不机械把全部字段放入 API;核对所有受影响消费者的兼容性。没有网络接口时用真实模块或文件边界,不强造 REST API。

按 图示方法 提供适用的架构、流程、ER 等图;用户指定的图不能无说明省略。按质量验证方法消减“不成立就会推翻路线”的假设,必要时修订整体方案或重新讨论选择,不能只标“未验证”就承诺可实施。

4. 深化与委派

按 专项设计要点 完成本次涉及的前端、后端或其他设计;裁剪无关内容,不把关键契约、数据或一致性决策留给使用者临场决定。

涉及表结构变更时,按专项中的“表用途与字段字典”解释表用途和字段含义,不只给 SQL 或 ER 图。

小型/单端任务自行完成。复杂且相对独立的专项按 设计委派协议 实际派发并等待子 agent;主 Agent 持有整体基线和共享契约。未解决依赖、同文件写入或共享产物冲突时不并行;无工具则自行处理,无名额可串行委派并说明。

5. 集成与完整性复核

主 Agent 核对证据并整合专项,检查需求、契约、图示、质量/失败场景、用户决策和验收相容,不能只拼接报告。专项提出契约变化时核对影响,触及重大取舍先与用户讨论,再同步基线及受影响结果。

按 方案完整度与使用说明 完成准备检查,区分草案、可实施、局部可实施与受阻;设计状态、用户选择和实施授权分别记录。未解决冲突或部分完成不能称为完整可实施。

6. HTML 交付与修订

按 HTML 设计文档 默认生成实际的 spec.html,完整保留方案、可见图示、适用范围和开放问题;专题较多时由统一入口导航,不重复维护 Markdown 正本。正式候选材料同样用 HTML,状态保持待决定;对话只给链接和关键摘要。

默认视觉母版为从当前 SKILL.md 所在目录解析的 ../_shared/assets/document-themes/blueprint.html。生成时读取并沿用其中的蓝图内联样式与文档骨架,直接写入本次内容,不每次重新设计主题;用户另有风格要求时优先。

优先用户位置或项目约定,已有需求目录时可同目录保存;无约定用目标项目 docs/design/YYYY-MM-DD-主题/spec.html。项目未定时用本任务可写产物目录,不写技能安装目录。用户明确格式/对话草稿要求及既有正本约定优先,不擅自搬迁。

交付后结束,由用户决定如何使用。后续要求修订时核对新证据,同步受影响的决定、契约、图示和状态;重大取舍仍与用户讨论,不要求经由固定流程返回。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.